A Lexical Resource of Hebrew Verb-Noun Multi-Word Expressions

A Lexical Resource of Hebrew Verb-Noun Multi-Word Expressions Chaya Liebeskind, Yaakov HaCohen-Kerner Department of Computer Science, Jerusalem College of Technology, Lev Academic Center 21 Havaad Haleumi St., P.O.B. 16031 9116001 Jerusalem, Israel liebchaya@gmail.com, kerner@jct.ac.il Abstract A verb-noun Multi-Word Expression (MWE) is a combination of a verb and a noun with or without other words, in which the combination has a meaning different from the meaning of the words considered separately. In this paper, we present a new lexical resource of Hebrew Verb-Noun MWEs (VN-MWEs). The VN-MWEs of this resource were manually collected and annotated from five different web resources. In addition, we analyze the lexical properties of Hebrew VN-MWEs by classifying them to three types: morphological, syntactic, and semantic. These two contributions are essential for designing algorithms for automatic VN-MWEs extraction. The analysis suggests some interesting features of VN-MWEs for exploration. The lexical resource enables to sample a set of positive examples for Hebrew VN-MWEs. This set of examples can either be used for training supervised algorithms or as seeds in unsupervised bootstrapping algorithms. Thus, this resource is a first step towards automatic identification of Hebrew VN-MWEs, which is important for natural language understanding, generation and translation systems. Keywords: Hebrew, Lexical Resource, Multi-Word Expression (MWE), Verb-Noun Multi-Word Expression 1. Introduction A Multi-Word Expression (MWE) is defined as any word combination for which the syntactic or semantic properties of the whole expression cannot be obtained from its parts (Sag et al., 2002). Examples of MWEs are phrasal verbs (calm down, get around), compounds (bus stop, washing machine), and idioms (break a leg, raining cats and dogs). The numerous MWEs pose a great challenge to the creation of Natural Language Processing (NLP) systems (Biber et al., 1999). They play an important role in NLP applications, such as semantic parsing and machine translation, which should not only identify them, but also deal with them when they are encountered (Fazly and Stevenson, 2007). In this research, we focus on a particular class of Hebrew MWEs that are formed from the combination of a verb with a noun. Each Hebrew Verb-Noun MWE (VN-MWE) func- tions as a single semantic unit and usually has an idiomatic meaning not predictable from the meanings of the individ- ual parts. Al-Haj (2009) presented a systematic linguistic characteri- zation of MWEs in Hebrew, and provided in a full picture of the diverse properties that Hebrew MWEs exhibit. How- ever, Al-Haj and Wintner (2010) limited their investigation to noun compounds. Although verb-noun MWEs acquisi- tion has been widely investigated in English, as far as we know, our research is a first attempt to focus specifically on this MWE type in Hebrew. The goal of our research is to manually construct a high quality publishable lexical resource of Hebrew VN-MWEs, which is a useful tool for supporting automatic extraction of additional VN-MWEs. Such a tool is important due to the fact that despite our efforts to make the lexical resource as comprehensive as possible, there are VN-MWEs that are not covered by …

Content truncated to 500 words